Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    punctuation and numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Thông
    -0.07
    roducing
    -0.07
    воль
    -0.07
    稠
    -0.06
     sentient
    -0.06
    ifty
    -0.06
    Commercial
    -0.06
    Beans
    -0.06
     nou
    -0.06
     retract
    -0.06
    POSITIVE LOGITS
    售价
    0.07
    istration
    0.07
    電子郵件
    0.07
    突击
    0.07
    情绪
    0.07
    价格上涨
    0.07
     الاجتماعية
    0.06
    毛巾
    0.06
    !".
    0.06
    ?type
    0.06
    Act Density 0.024%

    No Known Activations